Browse
Submit Data
Databases
API
Help

Dataset Information

20 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A High-Fidelity Model to Predict Length-of-Stay in the Neonatal Intensive Care Unit (NICU).

ABSTRACT: Having an interpretable dynamic length-of-stay (LOS) model can help hospital administrators and clinicians make better decisions and improve the quality of care. The widespread implementation of electronic medical record (EMR) systems has enabled hospitals to collect massive amounts of health data. However, how to integrate this deluge of data into healthcare operations remains unclear. We propose a framework grounded in established clinical knowledge to model patients' lengths-of-stay. In particular, we impose expert knowledge when grouping raw clinical data into medically meaningful variables, which summarize patients' health trajectories. We use dynamic predictive models to output patients' remaining lengths-of-stay (RLOS), future discharges, and census probability distributions based on their health trajectories up to the current stay. Evaluated with large-scale EMR data, the dynamic model significantly improves predictive power over the performance of any model in previous literature and remains medically interpretable.

SUBMITTER: Wang K

PROVIDER: S-EPMC9262254 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Neonatal intensive care unit: predictive models for length of stay.

Project description:Hospital length of stay (LOS) is important to administrators and families of neonates admitted to the neonatal intensive care unit (NICU). A prediction model for NICU LOS was developed using predictors birth weight, gestational age and two severity of illness tools, the score for neonatal acute physiology, perinatal extension (SNAPPE) and the morbidity assessment index for newborns (MAIN).Consecutive admissions (n=293) to a New England regional level III NICU were retrospectively collected. Multiple predictive models were compared for complexity and goodness-of-fit, coefficient of determination (R (2)) and predictive error. The optimal model was validated prospectively with consecutive admissions (n=615). Observed and expected LOS was compared.The MAIN models had best Akaike's information criterion, highest R (2) (0.786) and lowest predictive error. The best SNAPPE model underestimated LOS, with substantial variability, yet was fairly well calibrated by birthweight category. LOS was longer in the prospective cohort than the retrospective cohort, without differences in birth weight, gestational age, MAIN or SNAPPE.LOS prediction is improved by accounting for severity of illness in the first week of life, beyond factors known at birth. Prospective validation of both MAIN and SNAPPE models is warranted.

| S-EPMC4073289 | biostudies-literature

Derivation and Validation of a Clinical Model to Predict Intensive Care Unit Length of Stay After Cardiac Surgery.

Project description:Background Across the globe, elective surgeries have been postponed to limit infectious exposure and preserve hospital capacity for coronavirus disease 2019 (COVID-19). However, the ramp down in cardiac surgery volumes may result in unintended harm to patients who are at high risk of mortality if their conditions are left untreated. To help optimize triage decisions, we derived and ambispectively validated a clinical score to predict intensive care unit length of stay after cardiac surgery. Methods and Results Following ethics approval, we derived and performed multicenter valida tion of clinical models to predict the likelihood of short (≤2 days) and prolonged intensive care unit length of stay (≥7 days) in patients aged ≥18 years, who underwent coronary artery bypass grafting and/or aortic, mitral, and tricuspid value surgery in Ontario, Canada. Multivariable logistic regression with backward variable selection was used, along with clinical judgment, in the modeling process. For the model that predicted short intensive care unit stay, the c-statistic was 0.78 in the derivation cohort and 0.71 in the validation cohort. For the model that predicted prolonged stay, c-statistic was 0.85 in the derivation and 0.78 in the validation cohort. The models, together termed the CardiOttawa LOS Score, demonstrated a high degree of accuracy during prospective testing. Conclusions Clinical judgment alone has been shown to be inaccurate in predicting postoperative intensive care unit length of stay. The CardiOttawa LOS Score performed well in prospective validation and will complement the clinician's gestalt in making more efficient resource allocation during the COVID-19 period and beyond.

| S-EPMC7763427 | biostudies-literature

Designing a bed-side system for predicting length of stay in a neonatal intensive care unit.

Project description:Increased length of stay (LOS) in intensive care units is directly associated with the financial burden, anxiety, and increased mortality risks. In the current study, we have incorporated the association of day-to-day nutrition and medication data of the patient during its stay in hospital with its predicted LOS. To demonstrate the same, we developed a model to predict the LOS using risk factors (a) perinatal and antenatal details, (b) deviation of nutrition and medication dosage from guidelines, and (c) clinical diagnoses encountered during NICU stay. Data of 836 patient records (12 months) from two NICU sites were used and validated on 211 patient records (4 months). A bedside user interface integrated with EMR has been designed to display the model performance results on the validation dataset. The study shows that each gestation age group of patients has unique and independent risk factors associated with the LOS. The gestation is a significant risk factor for neonates < 34 weeks, nutrition deviation for < 32 weeks, and clinical diagnosis (sepsis) for ≥ 32 weeks. Patients on medications had considerable extra LOS for ≥ 32 weeks' gestation. The presented LOS model is tailored for each patient, and deviations from the recommended nutrition and medication guidelines were significantly associated with the predicted LOS.

| S-EPMC7870925 | biostudies-literature

Swab samples from a hospital neonatal intensive care unit (NICU)

Project description:Characterization of bacterial communities in a hospital NICU during a Serratia marcescens outbreak

| PRJNA432186 | ENA

intensive care unit

Project description:intensive care unit Raw sequence reads

| PRJNA561526 | ENA

Metabolic Acidosis in Preterm Infants is Associated with a Longer Length of Stay in the Neonatal Intensive Care Unit.

Project description:IntroductionPreterm births account for disproportionately high healthcare costs, in large part due to expenses related to length of stay in the hospital neonatal intensive care unit (NICU). It is common for preterm infants to receive human milk fortifier (HMF) while in the NICU. Liquid HMF is available in both acidified and non-acidified formulations. A recent randomized clinical trial found that acidified HMF is associated with an increased incidence of metabolic acidosis, which may contribute to increased costs and longer NICU length of stay.ObjectiveThe present study is a secondary analysis of these data, seeking to determine whether additional factors contribute to metabolic acidosis, whether metabolic acidosis is associated with longer hospital length of stay, and whether these associations contribute to the burden of hospital costs.MethodsThe study sample consisted of 152 infants who were hospitalized in US NICUs. Multiple logistic regression was used to model the NICU length of stay. Data from the 2012 Healthcare Cost and Utilization Project (HCUP) Kids' Inpatient Database (KID) were used to calculate the average cost (charge) per day in a NICU. Costs (charges) were adjusted to $US, year 2018 values, using the health Consumer Price Index.ResultResults indicated that acidified HMF was a strong predictor of metabolic acidosis, more so than gestational age or birth weight. Furthermore, metabolic acidosis was associated with incremental NICU costs (charges) of $US19,002 ($US65,462) per infant and longer NICU LOS.ConclusionFuture studies should further investigate factors that contribute to NICU length of stay and associated costs of care.Trial registrationClinicalTrials.gov: NCT02307760.

| S-EPMC7426333 | biostudies-literature

Non-invasive neurally adjusted ventilatory assist (NIV-NAVA) in the neonatal intensive care unit (NICU): an Australian NICU experience.

Project description:BackgroundPreterm infants often require non-invasive breathing support while their lungs and control of respiration are still developing. Non-invasive neurally adjusted ventilatory assist (NIV-NAVA) is an emerging technology that allows infants to breathe spontaneously while receiving support breaths proportional to their effort. This study describes the first Australian Neonatal Intensive Care Unit (NICU) experience of NIV-NAVA.MethodsRetrospective cohort study of infants admitted to a major tertiary NICU between October 2017 and April 2021 supported with NIV-NAVA. Infants were divided into three groups based on the indication to initiate NIV-NAVA (post-extubation; apnoea; escalation). Successful application of NIV-NAVA was based on the need for re-intubation within 48 h of application.ResultsThere were 169 NIV-NAVA episodes in 122 infants (82 post-extubation; 21 apnoea; 66 escalation). The median (range) gestational age at birth was 25 + 5 weeks (23 + 1 to 43 + 3 weeks) and median (range) birthweight was 963 g (365-4320 g). At NIV-NAVA application, mean (SD) age was 17 days (18.2), and median (range) weight was 850 g (501-4310 g). Infants did not require intubation within 48 h in 145/169 (85.2%) episodes [72/82 (87.8%) extubation; 21/21 (100%) apnoea; 52/66 (78.8%) escalation).ConclusionNIV-NAVA was successfully integrated for the three main indications (escalation; post-extubation; apnoea). Prospective clinical trials are still required to establish its effectiveness versus other modes of non-invasive support.

| S-EPMC11312715 | biostudies-literature

Comparison of Infant Gut and Skin Microbiota, Resistome and Virulome Between Neonatal Intensive Care Unit (NICU) Environments.

Project description:Background: There is a growing move to provide care for premature infants in a single family, private room neonatal intensive care unit (NICU) in place of the traditional shared space, open bay NICU. The resultant effect on the developing neonatal microbiota is unknown. Study Design: Stool and groin skin swabs were collected from infants in a shared-space NICU (old NICU) and a single-family room NICU (new NICU) on the same hospital campus. Metagenomic sequencing was performed and data analyzed by CosmosID bioinformatics software package. Results: There were no significant differences between the cohorts in gestational age, length of stay, and delivery mode; infants in the old NICU received significantly more antibiotics (p = 0.03). Differentially abundant antimicrobial resistance genes and virulence associated genes were found between the cohorts in stool and skin, with more differentially abundant antimicrobial resistance genes in the new NICU. The entire bacterial microbiota analyzed to the genus level significantly differed between cohorts in skin (p = 0.0001) but not in stool samples. There was no difference in alpha diversity between the two cohorts. DNA viruses and fungi were detected but did not differ between cohorts. Conclusion: Differences were seen in the resistome and virulome between the two cohorts with more differentially abundant antimicrobial resistance genes in the new NICU. This highlights the influence that different NICU environments can have on the neonatal microbiota. Whether the differences were due to the new NICU being a single-family NICU or located in a newly constructed building warrants exploration. Long term health outcomes from the differences observed must be followed longitudinally.

| S-EPMC6026636 | biostudies-literature

Measurement Error Due to Patient Flow in Estimates of Intensive Care Unit Length of Stay.

Project description:Clinical endpoints measured in terms of duration, such as intensive care unit (ICU) length of stay (LOS), are widely used in randomized clinical trials (RCTs) and observational research. In analyses of patient-level data from a recent RCT, in which ICU LOS was the primary endpoint, and in administrative data, we showed that additional ICU time is often accrued by patients after they are deemed ready for discharge. This "immutable" time (which cannot plausibly be altered by interventions under study) varies by day, week, and year, adding on average one-third of a day to total LOS. We then used statistical simulations, informed by the administrative data and RCT, to assess the impact of immutable time on the measurement and statistical comparison of patients' ICU LOS. These simulations demonstrated that immutable time combines with clinically necessary ICU time (neither of which is likely to be normally distributed) to produce overall LOS distributions that might either mask true treatment effects or suggest false treatment effects relative to analyses of time to discharge readiness. The extent and direction of bias were complex functions of the statistical method used, mortality rates and distributions, and the magnitude of immutable time relative to intervention-associated reductions in LOS.

| S-EPMC5860585 | biostudies-literature

The NICU Cuddler Curriculum: A Service-Learning Curriculum for Preclinical Medical Students in the Neonatal Intensive Care Unit.

Project description:IntroductionThe neonatal intensive care unit (NICU) is often seen as off-limits by preclinical medical students. The NICU cuddler curriculum is a service-learning curriculum that invited preclinical medical students into the NICU to engage with and learn from one of the hospital's most vulnerable populations: neonates. The purpose of this preclinical experience was to provide students with exposure to the NICU and an opportunity to engage with babies, families, and the NICU staff, in order to improve students' clinical and communication skills.MethodsFirst- and second- year medical students applied and were selected for participation. Participants cuddled neonates in the NICU for at least 10 hours, attended didactic sessions relevant to neonatal care, and debriefed with an attending each semester. The curriculum was evaluated via qualitative analysis and postparticipation surveys.ResultsTo date, a total of 73 students have participated in the NICU cuddler curriculum. Qualitative analysis revealed students felt included in patient care, empowered in their understanding of the social determinants of health, and useful in their role. A postsurvey of clinical medical students following participation revealed the sustained impact of this program.DiscussionThis service-learning curriculum for preclinical medical students has the potential to enhance student understanding of the social determinants of health, increase exposure to the NICU, and promote interprofessional collaboration, ultimately increasing preparedness of students for their clinical years.

| S-EPMC7809928 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data